Related Experiment Video
Updated: May 25, 2025
Patient Directed Recording of a Bipolar Three-Lead Electrocardiogram using a Smartwatch with ECG Function
Published on: December 11, 2019
Automated loss of pulse detection on a consumer smartwatch
Kamal Shah1, Anran Wang1, Yiwen Chen1
1Google Research, Mountain View, CA, USA.
Insights
A smartwatch algorithm using photoplethysmography can detect sudden loss of pulse, a key cardiac arrest sign. This technology aims to improve survival rates by enabling faster emergency medical response while minimizing false alarms.
Area of Science:
- Biomedical Engineering
- Cardiology
- Artificial Intelligence
Background:
- Out-of-hospital cardiac arrest is a critical emergency where rapid intervention is vital for survival.
- Sudden, unwitnessed cardiac arrest has a very low survival rate, emphasizing the need for timely detection and medical assistance.
- Automated detection systems must balance sensitivity with minimizing false positives to avoid overwhelming emergency services.
Purpose of the Study:
- To develop and validate a machine learning algorithm for a smartwatch to detect sudden loss of pulse, a primary indicator of cardiac arrest.
- To assess the algorithm's performance at a scale suitable for societal deployment.
- To evaluate the potential of wearable biosensors in improving cardiac arrest survivability.
Main Methods:
- Utilized photoplethysmography (PPG) signals from a smartwatch to identify patterns similar to pulselessness during cardiac arrest (ventricular fibrillation) and induced arterial occlusion.
- Developed and validated a loss of pulse detection algorithm using data from peripheral pulselessness and real-world (free-living) conditions.
- Conducted prospective evaluations of the end-to-end algorithm in simulation and real-world settings.
Main Results:
- The developed algorithm demonstrated that wearable PPG signals during induced pulselessness resemble those during ventricular fibrillation.
- Prospective evaluation showed an unintentional emergency call rate of 1 per 21.67 user-years.
- The algorithm achieved a sensitivity of 67.23% in a prospective cardiac arrest simulation model.
Conclusions:
- A multimodal, machine learning algorithm integrated into a smartwatch shows promise for detecting sudden loss of pulse.
- The technology is potentially deployable at a societal scale, offering an opportunity to improve cardiac arrest outcomes.
- The system demonstrates a balance between detecting critical events and minimizing the societal cost of false alarms.
Abstract:
Out-of-hospital cardiac arrest is a time-sensitive emergency that requires prompt identification and intervention: sudden, unwitnessed cardiac arrest is nearly unsurvivable1-3. A cardinal sign of cardiac arrest is sudden loss of pulse4. Automated biosensor detection of unwitnessed cardiac arrest, and dispatch of medical assistance, may improve survivability given the substantial prognostic role of time3,5, but only if the false-positive burden on public emergency medical systems is minimized5-7. Here we show that a multimodal, machine learning-based algorithm on a smartwatch can reach performance thresholds making it deployable at a societal scale. First, using photoplethysmography, we show that wearable photoplethysmography measurements of peripheral pulselessness (induced through an arterial occlusion model) manifest similarly to pulselessness caused by a common cardiac arrest arrhythmia, ventricular fibrillation. On the basis of the similarity of the photoplethysmography signal (from ventricular fibrillation or arterial occlusion), we developed and validated a loss of pulse detection algorithm using data from peripheral pulselessness and free-living conditions. Following its development, we evaluated the end-to-end algorithm prospectively: there was 1 unintentional emergency call per 21.67 user-years across two prospective studies; the sensitivity was 67.23% (95% confidence interval of 64.32% to 70.05%) in a prospective arterial occlusion cardiac arrest simulation model. These results indicate an opportunity, deployable at scale, for wearable-based detection of sudden loss of pulse while minimizing societal costs of excess false detections7.
More Related Videos
Related Concept Videos
01:30Pulse rhythm
Conversely, an irregular pulse pattern is termed dysrhythmia, stemming from disruptions in cardiac...
01:13Special considerations while measuring pulse
01:16Pulse
The pulse serves as a clinical...
01:30Equipments Used To Measure Blood Pressure
This invasive approach involves cannulating a peripheral artery. During each cardiac contraction, pressure generates mechanical motion within the catheter, transmitted through rigid, fluid-filled tubing to a transducer. This transducer converts mechanical motion into electrical signals displayed as waveforms on a monitor. An automatic flushing system prevents blood backflow. Due to the potential risk of unexpected arterial blood loss, this method is primarily used in intensive...
01:25Assessment of apical radial pulse
The A-R pulse assessment involves simultaneous evaluation of the apical and radial pulses. When the apical and radial pulse rates vary, this assessment helps identify a pulse deficit.
Pre-Procedural Preparation
01:11Assessment of radial pulse
The radial pulse, located at the wrist, is often the preferred site for assessing peripheral pulse because of its accessibility and dependability. The process of determining the radial pulse involves several steps: